Leonxlnx/taste-skill
Taste Skill provides portable AI Agent Skills designed to enhance the quality of AI-generated frontends and image-based design references, aiming to eliminate generic UI outputs.
Awesome AI Agents › AI Developer Toolkit
sigoden/llm-functions
LLM Functions is a project designed to simplify the creation of powerful language model (LLM) tools and agents by using plain Bash, JavaScript, and Python functions. It leverages the function calling capabilities of modern LLMs to directly connect these models to custom code, enabling users to execute system commands, process data, and interact with APIs seamlessly. This approach eliminates the need for complex integrations, making it accessible for developers familiar with these common programming languages. The project includes a showcase of tools and agents that demonstrate its capabilities. It requires some prerequisites such as the argc command-line framework and jq JSON processor. The primary CLI tool supporting LLM Functions is AIChat, which integrates with LLM Functions to utilize the created tools and agents. Users can build their own tools by writing simple scripts in Bash, JavaScript, or Python, with the project automatically generating the necessary JSON declarations based on comments in the code. The project also supports creating custom agents, which combine prompts, tools, and documents to form intelligent assistants similar to OpenAI's GPTs. Agents are defined with a structured folder layout and configuration files that specify their behavior and resources. Additionally, LLM Functions supports the Model Context Protocol (MCP), allowing tools and agents to be used through MCP servers and bridges, facilitating interoperability with external MCP tools. Comprehensive documentation is provided, including guides for tools, agents, and the argc command system. Overall, LLM Functions empowers developers to harness the full potential of LLMs by creating customizable, script-based tools and agents that can be easily integrated into various workflows, enhancing automation and AI interaction capabilities.
https://github.com/sigoden/llm-functions
Also in AI Developer Toolkit
unslothai/unsloth
Unsloth is a toolkit for fine-tuning and reinforcement learning of large language models, enabling faster training with significantly reduced VRAM usage across various advanced models and tasks.
reworkd/AgentGPT
AgentGPT is an open-source platform that allows users to assemble, configure, and deploy autonomous AI agents in a web browser to pursue custom goals by generating and executing tasks independently.
Gitlawb/openclaude
OpenClaude is an open-source command-line interface (CLI) coding-agent that supports various cloud and local model providers for unified AI-driven development workflows.
virgiliojr94/book-to-skill
A command-line tool that converts technical books, document folders or globs into structured agent skills in the open SKILL.md format, so coding agents load only the chapter relevant to a question.
google/adk-python
An open-source Python toolkit by Google for building, evaluating, and deploying sophisticated AI agents with flexibility, modularity, and integration within the Google ecosystem.
can1357/oh-my-pi
Oh My Pi is an AI coding agent for the terminal featuring hash-anchored edits, an optimized tool harness, LSP integration, and support for Python, browsers, and subagents.
millionco/react-doctor
React Doctor is an intelligent agent designed to diagnose and fix issues within React codebases, leveraging AI to improve code quality and developer efficiency.